Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 371 204 936 809 476 335 971  31  35 807 710 603 700 984 816 415 794 952  12 872
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 710  12  35 700  NA 952 807 603 371 335 476 816 936 872 204 415 971 984 794 809  NA  31  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 4 1 2 4 4 2 1 1 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y"
[26] "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y"
[26] "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "i" "z" "j" "e" "k" "Z" "O" "J" "D" "A"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  3  7 14 18
which( manyNumbersWithNA > 900 )
[1]  6 13 17 18
which( is.na( manyNumbersWithNA ) )
[1]  5 21 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 936 971 984 952
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 936 971 984 952
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 936 971 984 952

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "Z" "O" "J" "D" "A"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "i" "z" "j" "e" "k"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE
[18] FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  1  5  6 16
sum( manyNumbers %in% 300:600 )
[1] 4

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "small" "small" "large" NA      "large" "large" "large" "small" "small" "small" "large"
[13] "large" "large" "small" "small" "large" "large" "large" "large" NA      "small" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "small"   "small"   "large"   "UNKNOWN" "large"   "large"   "large"   "small"   "small"  
[11] "small"   "large"   "large"   "large"   "small"   "small"   "large"   "large"   "large"   "large"  
[21] "UNKNOWN" "small"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 710   0   0 700  NA 952 807 603   0   0   0 816 936 872   0   0 971 984 794 809  NA   0  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 4 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  4  2
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 18
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 984
which.min( manyNumbersWithNA )
[1] 2
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 12
range( manyNumbersWithNA, na.rm = TRUE )
[1]  12 984

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 710  12  35 700  NA 952 807 603 371 335 476 816 936 872 204 415 971 984 794 809  NA  31  NA
sort( manyNumbersWithNA )
 [1]  12  31  35 204 335 371 415 476 603 700 710 794 807 809 816 872 936 952 971 984
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  12  31  35 204 335 371 415 476 603 700 710 794 807 809 816 872 936 952 971 984  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 984 971 952 936 872 816 809 807 794 710 700 603 476 415 371 335 204  35  31  12  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 710  12  35 700  NA
order( manyNumbersWithNA[1:5] )
[1] 2 3 4 1 5
rank( manyNumbersWithNA[1:5] )
[1] 4 1 2 3 5
sort( mixedLetters )
 [1] "A" "D" "e" "i" "j" "J" "k" "O" "z" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 9.5 3.0 9.5 1.5 4.0 1.5 6.5 6.5 6.5 6.5
rank( manyDuplicates, ties.method = "min" )
 [1] 9 3 9 1 4 1 5 5 5 5
rank( manyDuplicates, ties.method = "random" )
 [1]  9  3 10  1  4  2  5  8  7  6

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -1.49653723  0.09693906  0.16086665
 [9]  0.29342774  1.10717287 -1.19709811  0.68313391 -0.70120855 -0.46496955 -0.27325418
round( v, 0 )
 [1] -1  0  0  0  1 -1  0  0  0  1 -1  1 -1  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -1.5  0.1  0.2  0.3  1.1 -1.2  0.7 -0.7 -0.5 -0.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -1.50  0.10  0.16  0.29  1.11 -1.20  0.68 -0.70 -0.46 -0.27
floor( v )
 [1] -1 -1  0  0  1 -2  0  0  0  1 -2  0 -1 -1 -1
ceiling( v )
 [1] -1  0  0  1  1 -1  1  1  1  2 -1  1  0  0  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC